{"id":"W2987837502","doi":"10.48550/arxiv.1911.02897","title":"Efficacy of Pixel-Level OOD Detection for Semantic Segmentation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Task (project management); Segmentation; Ranking (information retrieval); Pixel; Metric (unit); Image (mathematics); Pattern recognition (psychology); Image segmentation; Computer vision; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001515015,0.00156976,0.001057611,0.002550501,0.0004907114,0.002444496,0.001449415,0.001620059,0.002047578],"category_scores_gemma":[0.005116996,0.0003245924,0.0006919499,0.0008982872,0.0008322055,0.002292788,0.001340813,0.001044951,0.001621026],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006267031,"about_ca_system_score_gemma":0.0008096849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003249455,"about_ca_topic_score_gemma":0.005832728,"domain_scores_codex":[0.9989657,0.0001376866,0.00005228864,0.0003798008,0.0003065441,0.0001579557],"domain_scores_gemma":[0.9984621,0.0006051817,0.0001418354,0.0003088974,0.0003564788,0.0001255115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001784652,0.000394379,0.01270382,0.0008472705,0.0003341559,0.0002028274,0.0002416326,0.04672056,0.1055854,0.002613739,0.011472,0.8170996],"study_design_scores_gemma":[0.00006539766,0.0004718922,0.02033591,0.0001290185,0.0002188358,0.0006134189,0.0003263448,0.8285699,0.1336911,0.006225123,0.009277758,0.00007527196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5926414,0.005383899,0.3556271,0.0008357068,0.000979776,0.0002229496,0.002437903,0.0154967,0.02637451],"genre_scores_gemma":[0.8749915,0.0008706816,0.1153447,0.0002051819,0.0001551701,0.00004087087,0.003911452,0.0007753476,0.003705007],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.003249455,"threshold_uncertainty_score":0.008012295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09812074925881781,"score_gpt":0.22490034947419,"score_spread":0.1267796002153722,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}